nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
☆144May 8, 2025Updated last year
Alternatives and similar repositories for nanoGRPO
Users that are interested in nanoGRPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Pytorch Implementation of "Zero-Shot Off-Policy Learning" (ICML 2026)☆25Feb 16, 2026Updated 8 months ago
- working implimention of deepseek MLA☆45Jan 8, 2025Updated last year
- minimal GRPO implementation from scratch☆105Mar 14, 2025Updated last year
- fuchsia: minimal libaray for RL on LLMs☆10Mar 8, 2026Updated 7 months ago
- streaming deep reinforcement learning but 4x faster with jax!☆19Jan 4, 2026Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A Pytorch Lightning WGAN-gp to generate faces☆11Jan 26, 2021Updated 5 years ago
- ☆45Mar 31, 2025Updated last year
- ☆69Mar 21, 2025Updated last year
- RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.☆81Feb 19, 2025Updated last year
- Actor-Sharer-Learner training framework for off-policy DRL algorithms☆22Dec 29, 2024Updated last year
- solving nethack together! @:@:@:@:@☆26Oct 2, 2026Updated last month
- ☆10Dec 10, 2024Updated last year
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,286Aug 27, 2025Updated last year
- Opinionated library for managing hyperparameters and mutable state of machine learning training systems.☆19Aug 4, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- OpenAI gym environments for goal-conditioned and language-conditioned reinforcement learning☆14Jan 27, 2026Updated 9 months ago
- A minimal implementation of Agentic RAG using GRPO☆17Jun 11, 2025Updated last year
- rl from zero pretrain, can it be done? yes.☆297Sep 28, 2025Updated last year
- Minimal hackable GRPO implementation☆347Jan 31, 2025Updated last year
- Minimal and highly hackable implementation of Looped Transformers with GPT☆26Mar 8, 2026Updated 7 months ago
- official implementation of ODICE☆19Jan 31, 2024Updated 2 years ago
- [CVPR 2026] Official PyTorch implementation of SelVA "Hear What Matters! Text-conditioned Selective Video-to-Audio Generation"☆18Mar 27, 2026Updated 7 months ago
- Official implementation of the RLC 2024 paper "Policy-Guided Diffusion"☆155Jul 19, 2024Updated 2 years ago
- Collection of autoregressive model implementation☆85Oct 1, 2026Updated last month
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆640Oct 7, 2025Updated last year
- A basic pure pytorch implementation of flash attention☆17Oct 28, 2024Updated 2 years ago
- ☆14Mar 2, 2025Updated last year
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,718Nov 21, 2025Updated 11 months ago
- Real-Time RTUs☆13Mar 20, 2026Updated 7 months ago
- ☆13Jan 3, 2022Updated 4 years ago
- LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations☆30May 21, 2025Updated last year
- This repository provides tutorial, which discusses running sample publisher and subscriber using multiple transports of point_cloud_trans…☆11Aug 26, 2026Updated 2 months ago
- This is a repo covers ai research papers pseudocodes☆18Jun 20, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2023] Code for paper "Internally Rewarded Reinforcement Learning"☆13Jul 21, 2023Updated 3 years ago
- ☆21Dec 22, 2020Updated 5 years ago
- Official Repository of Six Dragons Fly Again (ISMIR 2024)☆18Updated this week
- Muon is Scalable for LLM Training☆1,557Aug 3, 2025Updated last year
- ☆18Aug 21, 2025Updated last year
- Toy meta-RL environments for testing algorithms implementations☆10Feb 21, 2024Updated 2 years ago
- An Open Source Claude Cowork alternative built with Codex CLI☆13Jan 29, 2026Updated 9 months ago